INDEX

Explanations

references to properties and styling in code

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Normdatei

-0.60

ScopeManager

-0.56

 فريبيس

-0.56

chyma

-0.54

StructEnd

-0.51

MENAFN

-0.51

MethodManager

-0.49

migrationBuilder

-0.49

ègre

-0.48

åde

-0.48

POSITIVE LOGITS

Alignment

0.92

ullable

0.64

posedge

0.64

 surla

0.63

 Alignment

0.62

hasOwnProperty

0.61

 antecedent

0.61

ensible

0.60

:✨

0.59

hdashline

0.59

Activations Density 0.004%

references to properties and styling in code

No Comments

No Known Activations